{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T04:10:22Z","timestamp":1791519022575,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA)"},{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202306079"],"award-info":[{"award-number":["tsqn202306079"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991411, 62002014"],"award-info":[{"award-number":["61991411, 62002014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project for Self-Developed Innovation Team of Jinan City","award":["2021GXRC038"],"award-info":[{"award-number":["2021GXRC038"]}]},{"name":"Young Elite Scientist Sponsorship Program by the China Association for Science and Technology","award":["2020QNRC001"],"award-info":[{"award-number":["2020QNRC001"]}]},{"name":"Hong Kong GRF-RGC General Research Fund","award":["11209819 (CityU 9042816), 11203820 (9042598)"],"award-info":[{"award-number":["11209819 (CityU 9042816), 11203820 (9042598)"]}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611982","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"406-416","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":76,"title":["Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-4008","authenticated-orcid":false,"given":"Runmin","family":"Cong","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University & Shandong University, Beijing & Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8038-7636","authenticated-orcid":false,"given":"Hongyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0492-2489","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-7261","authenticated-orcid":false,"given":"Sam","family":"Kwong","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202241"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028289"},{"key":"e_1_3_2_1_3_1","volume-title":"Global Context-Aware Progressive Aggregation Network for Salient Object Detection. In Thirty-Fourth AAAI Conference on Artificial Intelligence. 10599--10606","author":"Chen Zuyao","year":"2020","unstructured":"Zuyao Chen, Qianqian Xu, Runmin Cong, and Qingming Huang. 2020. Global Context-Aware Progressive Aggregation Network for Salient Object Detection. In Thirty-Fourth AAAI Conference on Artificial Intelligence. 10599--10606."},{"key":"e_1_3_2_1_4_1","volume-title":"An In Depth View of Saliency. In British Machine Vision Conference. 1--11","author":"Ciptadi Arridhana","unstructured":"Arridhana Ciptadi, Tucker Hermans, and James M. Rehg. 2013. An In Depth View of Saliency. In British Machine Vision Conference. 1--11."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233883"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870832"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932005"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3205182"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3220250"},{"key":"e_1_3_2_1_11_1","first-page":"1920","article-title":"c","volume":"53","author":"Cong Runmin","year":"2023","unstructured":"Runmin Cong, Ning Yang, Chongyi Li, Huazhu Fu, Yao Zhao, Qingming Huang, and Sam Kwong. 2023 c. Global-and-local Collaborative Learning for Co-Salient Object Detection. IEEE Trans. Cybern., Vol. 53, 3 (2023), 1920--1931.","journal-title":"Global-and-local Collaborative Learning for Co-Salient Object Detection. IEEE Trans. Cybern."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Runmin Cong Kepu Zhang Chen Zhang Feng Zheng Yao Zhao Qingming Huang and Sam Kwong. early access doi: 10.1109\/TMM.2022.3216476. Does Thermal Really Always Matter for RGB-T Salient Object Detection? IEEE Trans. Multimedia (early access doi: 10.1109\/TMM.2022.3216476).","DOI":"10.1109\/TMM.2022.3216476"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3123984"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations. 1--21","author":"Dosovitskiy Alexey","unstructured":"Alexey Dosovitskiy and Lucas Beyer et al. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. 1--21."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073689"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1021"},{"key":"e_1_3_2_1_20_1","volume-title":"Squeeze-and-excitation Networks. In IEEE Conference on Computer Vision and Pattern Recognition. 7132--7141","author":"Hu Jie","year":"2018","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation Networks. In IEEE Conference on Computer Vision and Pattern Recognition. 7132--7141."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3214092"},{"key":"e_1_3_2_1_22_1","volume-title":"Calibrated RGB-D Salient Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 9471--9481","author":"Ji Wei","year":"2021","unstructured":"Wei Ji, Jingjing Li, Shuang Yu, Miao Zhang, Yongri Piao, Shunyu Yao, Qi Bi, Kai Ma, Yefeng Zheng, Huchuan Lu, and Li Cheng. 2021. Calibrated RGB-D Salient Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 9471--9481."},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Jiang Yangbangyan","year":"2019","unstructured":"Yangbangyan Jiang, Qianqian Xu, Zhiyong Yang, Xiaochun Cao, and Qingming Huang. 2019. DM2C: Deep Mixed-Modal Clustering. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060167"},{"key":"e_1_3_2_1_25_1","volume-title":"Occlusion-aware Bi-directional Guided Network for Light Field Salient Object Detection. In ACM International Conference on Multimedia. 1692--1701","author":"Jing Dong","year":"2021","unstructured":"Dong Jing, Shuo Zhang, Runmin Cong, and Youfang Lin. 2021. Occlusion-aware Bi-directional Guided Network for Light Field Salient Object Detection. In ACM International Conference on Multimedia. 1692--1701."},{"key":"e_1_3_2_1_26_1","volume-title":"SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection. In European Conference on Computer Vision. 630--647","author":"Lee Minhyeok","year":"2022","unstructured":"Minhyeok Lee, Chaewon Park, Suhwan Cho, and Sangyoun Lee. 2022. SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection. In European Conference on Computer Vision. 630--647."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2969255"},{"key":"e_1_3_2_1_28_1","volume-title":"RGB-D Salient Object Detection with Cross-modality Modulation and Selection. In European Conference on Computer Vision. 225--241","author":"Li Chongyi","year":"2020","unstructured":"Chongyi Li, Runmin Cong, Yongri Piao, Qianqian Xu, and Chen Change Loy. 2020. RGB-D Salient Object Detection with Cross-modality Modulation and Selection. In European Conference on Computer Vision. 225--241."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062689"},{"key":"e_1_3_2_1_30_1","volume-title":"Saliency Detection on Light Field. In IEEE Conference on Computer Vision and Pattern Recognition. 2806--2813","author":"Li Nianyi","year":"2014","unstructured":"Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, and Jingyi Yu. 2014. Saliency Detection on Light Field. In IEEE Conference on Computer Vision and Pattern Recognition. 2806--2813."},{"key":"e_1_3_2_1_31_1","volume-title":"Visual Saliency Transformer. In IEEE\/CVF International Conference on Computer Vision. 4702--4712","author":"Liu Nian","year":"2021","unstructured":"Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, and Junwei Han. 2021c. Visual Saliency Transformer. In IEEE\/CVF International Conference on Computer Vision. 4702--4712."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"e_1_3_2_1_34_1","volume-title":"Leveraging Stereopsis for Saliency Analysis. In IEEE Conference on Computer Vision and Pattern Recognition. 454--461","author":"Niu Yuzhen","year":"2012","unstructured":"Yuzhen Niu, Yujie Geng, Xueqing Li, and Feng Liu. 2012. Leveraging Stereopsis for Saliency Analysis. In IEEE Conference on Computer Vision and Pattern Recognition. 454--461."},{"key":"e_1_3_2_1_35_1","volume-title":"RGBD Salient Object Detection: A Benchmark and Algorithms. In European Conference on Computer Vision. 92--109","author":"Peng Houwen","year":"2014","unstructured":"Houwen Peng, Bing Li, Weihua Xiong, Weiming Hu, and Rongrong Ji. 2014. RGBD Salient Object Detection: A Benchmark and Algorithms. In European Conference on Computer Vision. 92--109."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00908"},{"key":"e_1_3_2_1_37_1","volume-title":"Exploiting Global Priors for RGB-D Saliency Detection. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. 25--32","author":"Ren Jianqiang","year":"2015","unstructured":"Jianqiang Ren, Xiaojin Gong, Lu Yu, Wenhui Zhou, and Michael Ying Yang. 2015. Exploiting Global Priors for RGB-D Saliency Detection. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. 25--32."},{"key":"e_1_3_2_1_38_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","volume-title":"Multi-Modal Transformer for RGB-D Salient Object Detection. In IEEE International Conference on Image Processing. 2466--2470","author":"Song Peipei","year":"2022","unstructured":"Peipei Song, Jing Zhang, Piotr Koniusz, and Nick Barnes. 2022. Multi-Modal Transformer for RGB-D Salient Object Detection. In IEEE International Conference on Image Processing. 2466--2470."},{"key":"e_1_3_2_1_40_1","volume-title":"Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion. In IEEE Conference on Computer Vision and Pattern Recognition. 1407--1417","author":"Sun Peng","year":"2021","unstructured":"Peng Sun, Wenhu Zhang, Huanyu Wang, Songyuan Li, and Xi Li. 2021. Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion. In IEEE Conference on Computer Vision and Pattern Recognition. 1407--1417."},{"key":"e_1_3_2_1_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140606"},{"key":"e_1_3_2_1_43_1","volume-title":"PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment. In IEEE\/CVF International Conference on Computer Vision. 9196--9205","author":"Wang Kaixin","year":"2019","unstructured":"Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, and Jiashi Feng. 2019. PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment. In IEEE\/CVF International Conference on Computer Vision. 9196--9205."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123548"},{"key":"e_1_3_2_1_45_1","volume-title":"Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16347--16356","author":"Wen Peisong","year":"2021","unstructured":"Peisong Wen, Qianqian Xu, Yangbangyan Jiang, Zhiyong Yang, Yuan He, and Qingming Huang. 2021a. Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16347--16356."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12063"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12071"},{"key":"e_1_3_2_1_48_1","volume-title":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection. In ACM International Conference on Multimedia. 2094--2102","author":"Zhang Chen","year":"2021","unstructured":"Chen Zhang, Runmin Cong, Qinwei Lin, Lin Ma, Feng Li, Yao Zhao, and Sam Kwong. 2021b. Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection. In ACM International Conference on Multimedia. 2094--2102."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00861"},{"key":"e_1_3_2_1_50_1","volume-title":"Asymmetric Two-stream Architecture for Accurate RGB-D Saliency Detection. In European Conference on Computer Vision. 374--390","author":"Zhang Miao","year":"2020","unstructured":"Miao Zhang, Sun Xiao Fei, Jie Liu, Shuang Xu, Yongri Piao, and Huchuan Lu. 2020b. Asymmetric Two-stream Architecture for Accurate RGB-D Saliency Detection. In European Conference on Computer Vision. 374--390."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042084"},{"key":"e_1_3_2_1_52_1","volume-title":"Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection. In ACM International Conference on Multimedia. 731--740","author":"Zhang Wenbo","year":"2021","unstructured":"Wenbo Zhang, Ge-Peng Ji, Zhuo Wang, Keren Fu, and Qijun Zhao. 2021c. Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection. In ACM International Conference on Multimedia. 731--740."},{"key":"e_1_3_2_1_53_1","volume-title":"BTS-Net: Bi-Directional Transfer-And-Selection Network for RGB-D Salient Object Detection. In IEEE International Conference on Multimedia and Expo. 1--6.","author":"Zhang Wenbo","year":"2021","unstructured":"Wenbo Zhang, Yao Jiang, Keren Fu, and Qijun Zhao. 2021d. BTS-Net: Bi-Directional Transfer-And-Selection Network for RGB-D Salient Object Detection. In IEEE International Conference on Multimedia and Expo. 1--6."},{"key":"e_1_3_2_1_54_1","volume-title":"MVSalNet: Multi-view Augmentation for RGB-D Salient Object Detection. In European Conference on Computer Vision. 270--287","author":"Zhou Jiayuan","year":"2022","unstructured":"Jiayuan Zhou, Lijun Wang, Huchuan Lu, Kaining Huang, Xinchu Shi, and Bocong Liu. 2022a. MVSalNet: Multi-view Augmentation for RGB-D Salient Object Detection. In European Conference on Computer Vision. 270--287."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0199-z"},{"key":"e_1_3_2_1_56_1","volume-title":"Specificity-preserving RGB-D Saliency Detection. In IEEE\/CVF International Conference on Computer Vision. 4661--4671","author":"Zhou Tao","year":"2021","unstructured":"Tao Zhou, Huazhu Fu, Geng Chen, Yi Zhou, Deng-Ping Fan, and Ling Shao. 2021b. Specificity-preserving RGB-D Saliency Detection. In IEEE\/CVF International Conference on Computer Vision. 4661--4671."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3077767"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611982","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:09:44Z","timestamp":1755821384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":57,"alternative-id":["10.1145\/3581783.3611982","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611982","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}